Model: SoLU Model: 12 Layers, 6144 Neurons per Layer

Dataset: 80% C4 (Web Text) and 20% Python Code

Neuron 4979 in Layer 0

Load this data into an Interactive Neuroscope

See Documentation here

Hooked Transformer Loading: HookedTransformer.from_pretrained('solu-12l')

Click the toggle to see the full text!

Text #0

Max Range: 0.2087. Min Range: -0.2087

Max Act: 0.2087. Min Act: -0.0001

Data Index: 1049498 (C4 (Web Text))

Max Activating Token Index: 49

Text #1

Max Range: 0.2087. Min Range: -0.2087

Max Act: 0.2042. Min Act: -0.0001

Data Index: 312962 (C4 (Web Text))

Max Activating Token Index: 245

Text #2

Max Range: 0.2087. Min Range: -0.2087

Max Act: 0.2002. Min Act: -0.0001

Data Index: 1492347 (Python Code)

Max Activating Token Index: 67

Text #3

Max Range: 0.2087. Min Range: -0.2087

Max Act: 0.2016. Min Act: -0.0001

Data Index: 1614439 (Python Code)

Max Activating Token Index: 469

Text #4

Max Range: 0.2087. Min Range: -0.2087

Max Act: 0.1996. Min Act: -0.0001

Data Index: 1442962 (Python Code)

Max Activating Token Index: 138

Text #5

Max Range: 0.2087. Min Range: -0.2087

Max Act: 0.2031. Min Act: -0.0001

Data Index: 1021520 (C4 (Web Text))

Max Activating Token Index: 116

Text #6

Max Range: 0.2087. Min Range: -0.2087

Max Act: 0.1967. Min Act: -0.0001

Data Index: 1458894 (Python Code)

Max Activating Token Index: 123

Text #7

Max Range: 0.2087. Min Range: -0.2087

Max Act: 0.1955. Min Act: -0.0001

Data Index: 1653110 (Python Code)

Max Activating Token Index: 448

Text #8

Max Range: 0.2087. Min Range: -0.2087

Max Act: 0.1981. Min Act: -0.0001

Data Index: 1417727 (Python Code)

Max Activating Token Index: 598

Text #9

Max Range: 0.2087. Min Range: -0.2087

Max Act: 0.1973. Min Act: -0.0001

Data Index: 348865 (C4 (Web Text))

Max Activating Token Index: 15

Text #10

Max Range: 0.2087. Min Range: -0.2087

Max Act: 0.1977. Min Act: -0.0001

Data Index: 1140842 (C4 (Web Text))

Max Activating Token Index: 612

Text #11

Max Range: 0.2087. Min Range: -0.2087

Max Act: 0.1965. Min Act: -0.0001

Data Index: 1641196 (Python Code)

Max Activating Token Index: 17

Text #12

Max Range: 0.2087. Min Range: -0.2087

Max Act: 0.1944. Min Act: -0.0002

Data Index: 158504 (C4 (Web Text))

Max Activating Token Index: 122

Text #13

Max Range: 0.2087. Min Range: -0.2087

Max Act: 0.1982. Min Act: -0.0001

Data Index: 1206441 (C4 (Web Text))

Max Activating Token Index: 22

Text #14

Max Range: 0.2087. Min Range: -0.2087

Max Act: 0.1936. Min Act: -0.0001

Data Index: 1298953 (C4 (Web Text))

Max Activating Token Index: 124

Text #15

Max Range: 0.2087. Min Range: -0.2087

Max Act: 0.1923. Min Act: -0.0001

Data Index: 1329122 (C4 (Web Text))

Max Activating Token Index: 161

Text #16

Max Range: 0.2087. Min Range: -0.2087

Max Act: 0.1924. Min Act: -0.0002

Data Index: 665878 (C4 (Web Text))

Max Activating Token Index: 23

Text #17

Max Range: 0.2087. Min Range: -0.2087

Max Act: 0.1923. Min Act: -0.0001

Data Index: 1498875 (Python Code)

Max Activating Token Index: 942

Text #18

Max Range: 0.2087. Min Range: -0.2087

Max Act: 0.1926. Min Act: -0.0001

Data Index: 1483693 (Python Code)

Max Activating Token Index: 418

Text #19

Max Range: 0.2087. Min Range: -0.2087

Max Act: 0.1916. Min Act: -0.0001

Data Index: 1448096 (Python Code)

Max Activating Token Index: 123